[Intel-gfx] [RFC 6/8] drm/i915: Add support for forwarding pid in timestamp sample metadata through perf

[sourab.gupta at intel.com]

From: Sourab Gupta <sourab.gupta at intel.com>

This patch introduces flags and adds support for having pid output with the
timestamp samples and forwarding them through perf.

When the userspace expresses its interest in listening to the pid through a
gen pmu attr field during event init, the samples generated would have an
additional field appended with the pid information.

Signed-off-by: Sourab Gupta <sourab.gupta at intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h     |  2 ++
 drivers/gpu/drm/i915/i915_oa_perf.c | 16 ++++++++++++++++
 include/uapi/drm/i915_drm.h         |  8 +++++++-
 3 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index cf0528e..c23c5be 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1683,6 +1683,7 @@ struct i915_gen_pmu_node {
 	bool discard;
 	u32 ctx_id;
 	u32 ring;
+	u32 pid;
 };
 
 extern const struct i915_oa_reg i915_oa_3d_mux_config_hsw[];
@@ -2013,6 +2014,7 @@ struct drm_i915_private {
 		struct work_struct work_timer;
 		struct work_struct work_event_destroy;
 #define I915_GEN_PMU_SAMPLE_RING		(1<<0)
+#define I915_GEN_PMU_SAMPLE_PID			(1<<1)
 		int sample_info_flags;
 	} gen_pmu;
 
diff --git a/drivers/gpu/drm/i915/i915_oa_perf.c b/drivers/gpu/drm/i915/i915_oa_perf.c
index 5915720..a195c37 100644
--- a/drivers/gpu/drm/i915/i915_oa_perf.c
+++ b/drivers/gpu/drm/i915/i915_oa_perf.c
@@ -124,6 +124,8 @@ void i915_gen_insert_cmd_ts(struct intel_ringbuffer *ringbuf, u32 ctx_id,
 	entry->ctx_id = ctx_id;
 	if (dev_priv->gen_pmu.sample_info_flags & I915_GEN_PMU_SAMPLE_RING)
 		entry->ring = ring_id_mask(ring);
+	if (dev_priv->gen_pmu.sample_info_flags & I915_GEN_PMU_SAMPLE_PID)
+		entry->pid = current->pid;
 	i915_gem_request_assign(&entry->req, ring->outstanding_lazy_request);
 
 	spin_lock_irqsave(&dev_priv->gen_pmu.lock, lock_flags);
@@ -556,6 +558,7 @@ static void forward_one_gen_pmu_sample(struct drm_i915_private *dev_priv,
 	u8 *snapshot, *current_ptr;
 	struct drm_i915_ts_node_ctx_id *ctx_info;
 	struct drm_i915_ts_node_ring_id *ring_info;
+	struct drm_i915_ts_node_pid *pid_info;
 	struct perf_raw_record raw;
 
 	ts_size = sizeof(struct drm_i915_ts_data);
@@ -573,6 +576,13 @@ static void forward_one_gen_pmu_sample(struct drm_i915_private *dev_priv,
 		current_ptr = snapshot + snapshot_size;
 	}
 
+	if (dev_priv->gen_pmu.sample_info_flags & I915_GEN_PMU_SAMPLE_PID) {
+		pid_info = (struct drm_i915_ts_node_pid *)current_ptr;
+		pid_info->pid = node->pid;
+		snapshot_size += sizeof(*pid_info);
+		current_ptr = snapshot + snapshot_size;
+	}
+
 	perf_sample_data_init(&data, 0, event->hw.last_period);
 
 	/* Note: the combined u32 raw->size member + raw data itself must be 8
@@ -1027,6 +1037,9 @@ static int init_gen_pmu_buffer(struct perf_event *event)
 	if (dev_priv->gen_pmu.sample_info_flags & I915_GEN_PMU_SAMPLE_RING)
 		node_size += sizeof(struct drm_i915_ts_node_ring_id);
 
+	if (dev_priv->gen_pmu.sample_info_flags & I915_GEN_PMU_SAMPLE_PID)
+		node_size += sizeof(struct drm_i915_ts_node_pid);
+
 	/* size has to be aligned to 8 bytes (required by relevant gpu cmds) */
 	node_size = ALIGN(node_size, 8);
 	dev_priv->gen_pmu.buffer.node_size = node_size;
@@ -1642,6 +1655,9 @@ static int i915_gen_event_init(struct perf_event *event)
 		dev_priv->gen_pmu.sample_info_flags |=
 				I915_GEN_PMU_SAMPLE_RING;
 
+	if (gen_attr.sample_pid)
+		dev_priv->gen_pmu.sample_info_flags |= I915_GEN_PMU_SAMPLE_PID;
+
 	/* To avoid the complexity of having to accurately filter
 	 * data and marshal to the appropriate client
 	 * we currently only allow exclusive access */
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index fd52926..393f4ec 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -103,7 +103,8 @@ typedef struct _drm_i915_oa_attr {
 struct drm_i915_gen_pmu_attr {
 	__u32 size;
 	__u32 sample_ring:1,
-		__reserved_1:31;
+		sample_pid:1,
+		__reserved_1:30;
 };
 
 /* Header for PERF_RECORD_DEVICE type events */
@@ -163,6 +164,11 @@ struct drm_i915_ts_node_ring_id {
 	__u32 pad;
 };
 
+struct drm_i915_ts_node_pid {
+	__u32 pid;
+	__u32 pad;
+};
+
 /* Each region is a minimum of 16k, and there are at most 255 of them.
  */
 #define I915_NR_TEX_REGIONS 255	/* table size 2k - maximum due to use
-- 
1.8.5.1